#計(jì)量經(jīng)濟(jì)學(xué)論文(eviews分析)-中國食品價(jià)格指數(shù)的影響因素分析

1、關(guān)鍵詞：食品價(jià)格指數(shù)多因素分析預(yù)測模型模型檢測與修正二、模型設(shè)定在本文中，我們選取糧食價(jià)格指數(shù)、肉禽及制品價(jià)格指數(shù)、水產(chǎn)品價(jià)格指數(shù)、蔬菜 價(jià)格指數(shù)作為解釋變量，選取食品價(jià)格指數(shù)作為被解釋變量，構(gòu)建多元線性回歸模型：Y=B 0+ B 1X1 + B 2X2 + B 3X3 + 0 4X4 + 仙 i其中：Y食品價(jià)格指數(shù)X1糧食價(jià)格指數(shù)X2肉禽價(jià)格指數(shù)X3水產(chǎn)品價(jià)格指數(shù)X4蔬菜價(jià)格指數(shù)三、模型的估計(jì)與調(diào)整通過使用Eviews計(jì)量經(jīng)濟(jì)學(xué)分析軟件，得到了一下回歸分析結(jié)果Dependent Variable: YMethod: Least SquaresDate: 05/03/14 Time: 19:5

2、0Sample: 2014:01 2014:04Included observations: 27VariableCoefficientStd. Errort-StatisticProb.C7.2991204.8192871.5145640.1441X10.4531110.0604837.4915000.0000X20.2255630.02100210.740120.0000X30.1764920.0642352.7475760.0118X40.0593710.0123924.7909120.0001R-squared0.990031Mean dependent var108.2515Adju

3、sted R-squared0.988219S.D.dependent var4.152074S.E. of regression0.450673Akaike info criterion1.409427Sum squared resid4.468336Schwarz criterion1.649396Log likelihood-14.02726F-statistic546.2222Durbin-Watson stat0.901780Prob(F-statistic)0.0000001 .多重共線性檢驗(yàn)。Correlation MatrixY| XIX2 X3X4Y1 0000000.804

4、6120.9393210.963383-0 639286XI0.B046121.0000000.6162700 7961544566700X20.9393210.6162701.0000000 882967-0.742045X30.9633830 7961540 8829671 0000004590832X40 639286-0.566700-0.742045-0.590B321.D0D0D0(1)直觀的來看，x1、x3的相關(guān)系數(shù)達(dá)到了 0.80 , x2、x3的相關(guān)系數(shù)達(dá)到了 0.88所以可以認(rèn)為存在較嚴(yán)重的多重共線性。(2)修正多重共線性現(xiàn)剔除x3進(jìn)行回歸，結(jié)果如下：Dependent V

5、ariable: YMethod: Least SquaresDate: 05/03/14 Time: 21:40Sample: 2014:01 2014:04Included observations: 27VariableCoefficientStd. Errort-StatisticProb.C5.2102285.3941020.9659120.3441X10.5787620.04486712.899600.0000X20.2749320.01232422.308120.0000X40.0758200.0122986.1650940.0000R-squared0.986610Mean d

6、ependent var108.2515Adjusted R-squared0.984864S.D.dependent var4.152074S.E. of regression0.510823Akaike info criterion1.630366Sum squared resid6.001621Schwarz criterion1.822342Log likelihood-18.00994F-statistic564.9205Durbin-Watson stat0.921999Prob(F-statistic)0.000000由上圖可看出，剔除x3后，擬合優(yōu)度非常好，且顯著性明顯。再剔除

7、x1進(jìn)行回歸，結(jié)果入下：Dependent Variable: Y Method: Least SquaresDate: 05/03/14 Time: 21:43Sample: 2014:01 2014:04R-squaredAdjusted R-squared0.9646010.959983Included observations: 27VariableCoefficientStd. Errort-StatisticProb.C32.394936.3853025.0733580.0000X20.1426790.0329004.3367320.0002X30.5403430.0774786.

8、9741530.0000X40.0144350.0199850.7222650.4774Mean dependent var 108.2515S.D. dependent var 4.152074S.E. of regression0.830589Akaike info criterion2.602589Sum squared resid15.86718Schwarz criterion2.794565Log likelihood-31.13496F-statistic208.9094Durbin-Watson stat1.044482Prob(F-statistic)0.000000由上圖可

9、以看出，1川除x1后,導(dǎo)致x4速/、過t檢驗(yàn)。剔除x2進(jìn)行回歸，結(jié)果如下:Dependent Variable: YMethod: Least SquaresDate: 05/03/14 Time: 21:41Sample: 2014:01 2014:04Included observations: 27VariableCoefficientStd. Error t-StatisticProb.C16.3409511.595881.4092020.1722X10.1109050.1256320.8827720.3865X30.7667330.0812689.4346090.0000X4-0.0

10、321650.021984-1.4630590.1570R-squared0.937763Mean dependent108.2515varAdjusted R-squared0.929645S.D. dependent var4.152074S.E. of regression1.101317Akaikeinfo3.166844criterionSum squared resid27.89668Schwarz criterion3.358820Log likelihood-38.75239F-statistic115.5183Durbin-Watson stat1.495176Prob(F-

11、statistic)0.000000由上圖可知，剔除x2后，導(dǎo)致x1, x4都通不過t檢驗(yàn)，且可決系數(shù)大幅降低剔除x4進(jìn)行回歸，結(jié)果入下：Dependent Variable: YMethod: Least Squares Date: 05/03/14 Time: 21:44Sample: 2014:01 2014:04Included observations: 27VariableCoefficient Std. Error t-Statistic Prob.C21.060075.4100843.8927440.0007X10.3128540.0739924.2282150.0003X20

12、.1563630.0213157.3358800.0000R-squared0.979631Mean dependent var108.2515Adjusted R-squared0.976974S.D. dependent var4.152074S.E. of regression0.630052Akaike info criterion2.049924Sum squared resid9.130200Schwarz criterion2.241900Log likelihood-23.67397F-statistic368.7162Durbin-Watson stat2.010366Pro

13、b(F-statistic)0.000000X30.3251700.0786274.1355880.0004由上圖可看出，x4的存在不影響本文的分析結(jié)果，沒必要剔除所以綜上所述，剔除x3,得到一下回歸分析結(jié)果：Dependent Variable: YMethod: Least SquaresDate: 05/31/12 Time: 21:40Sample: 2014:01 2014:04Included observations: 27VariableCoefficientStd. Errort-StatisticProb.C5.2102285.3941020.9659120.3441X10

14、.5787620.04486712.899600.0000X20.2749320.01232422.308120.0000X40.0758200.0122986.1650940.0000R-squared0.986610Mean dependent var108.2515Adjusted R-squared0.984864S.D.dependent var4.152074S.E. of regression0.510823Akaike info criterion1.630366Sum squared resid6.001621Schwarz criterion1.822342Log like

15、lihood-18.00994F-statistic564.9205Durbin-Watson stat0.921999Prob(F-statistic)0.000000彳馬至U的回歸方程為 Y=5.210228 +0.578762X1 +0.274932X2 +0.07582X4(0.965912)(12.8996)(22.3081)(6.165094)R2=0.9866Adjusted R-squared =0.9849F=564.9205從回歸的結(jié)果可以得到 R2=0.9866,修正的可決系數(shù)為0.9849,這說明模型對(duì)樣本 的擬合度非常好。2 .相關(guān)性檢驗(yàn)從估計(jì)的結(jié)果可以看出，模型擬合

16、較好，可決系數(shù)R2=0.9866,修正的可決系數(shù)為 0.9849 ,表明模型在整體上擬合比較好r 12D1D.D110 0711：0111：07| Rg.id向Actu 自 I :. Ftt里3 .顯著性檢驗(yàn)(1)對(duì)于？1, t統(tǒng)計(jì)量為12.8996。給定a =0.05,查t分布表，在自由度為n-4=23 下，得臨界值t0.025(23)=2.069 ,因?yàn)閠>t0.025(23),所以拒絕原假設(shè) H0: ?1=0 ,表 明糧食價(jià)格指數(shù)對(duì)食品價(jià)格指數(shù)有顯著性影響；(2)對(duì)于？2, t統(tǒng)計(jì)量為22.3081。給定a =0.05,查t分布表，在自由度為n-4=23 下，得臨界值t0.025(

17、23)= 2.069 ,因?yàn)閠>t0.025(23),所以拒絕原假設(shè) H0: ?2=0 ,表 明肉禽價(jià)格指數(shù)對(duì)食品價(jià)格指數(shù)有顯著性影響。(3)對(duì)于？4, t統(tǒng)計(jì)量為6.165094。給定a =0.05 ,查t分布表，在自由度為n-4=23 下，得臨界值t0.025(23)= 2.069 ,因?yàn)閠>t0.025(23),所以拒絕原假設(shè) H0: ?4=0 ,表 明蔬菜價(jià)格指數(shù)對(duì)食品價(jià)格指數(shù)有顯著性影響。(4)對(duì)于F=564.9205>F(3,23)=3.03(顯著性水平為0.05),表明模型從整體上看食 品價(jià)格指數(shù)與各解釋變量之間線性關(guān)系顯著。4序列相關(guān)檢驗(yàn)AC PAC Q-St

18、at ProbAutocorrelation Partial Correfationj1 0 519 0 519 3.1067 0 00412 -0 037 -0419 8.1488 0.01713 -0428 -0.305 14 120 0 00314566 -0 282 25.009 0.000這15 -0 444 -XJ.225 32 022 0 0001 (6 Q059 G.035 32.152 0.000n17 0 197 -0 196 33 667 0 00018 0 234 心 218 35 922 0 00019 Q 127 -0 216 36 622 0.000i110 0

19、061 -0.037 36792 0.000ZJi11 0 143 0 272 37.739 0 000!112 0 019 -0 291 37.809 0.000(1)由圖可知，存在一階自相關(guān)。(2)修正：用科克倫-奧克特迭代方程法對(duì)模型進(jìn)行修正，得到如下結(jié)果:Dependent Variable: YMethod: Least SquaresDate: 05/03/14 Time: 13:10Sample(adjusted): 2014:01 2014:04Included observations: 26 after adjusting endpointsConvergence achi

20、eved after 10 iterationsVariableCoefficientStd.Errort-StatisticProb.C5.1691879.8464600.5249790.6051X10.5631620.0877866.4151880.0000X20.2821290.01771215.928550.0000X40.0845860.0103308.1882700.0000AR(1)0.5840820.1869773.1238250.0051R-squared0.989380Mean dependent var108.5496Adjusted R-squared0.987357S

21、.D. dependent var3.928543S.E. of regression0.441736Akaike info criterion1.374831Sum squared resid4.097737Schwarz criterion1.616772Log likelihood-12.87280F-statistic489.0816Durbin-Watson stat1.380596Prob(F-statistic)0.000000Inverted AR Roots.58得到一階自相關(guān)系數(shù)估計(jì)為0.584082再次檢驗(yàn)是否存在自相關(guān)：Autocorrelation Partial C

22、orrelationAC PAC Q-Stat Prab1 0.298 口 2982.57972 -0.120 -0 2293.01970 0E23 -0.309 -0 2286 04930 0494 -0.358 -0 25S10.2970 0165 -0.335 -0.31514/1770 0076 -0,014 -0 043U.1840 0147 0.162 -0 10B15.1920.0198 0,165 -0 13516.2990 0239 0 081 -0 15316 5810 03510 0.001 0 15216.5810 05611 0.195 0 287184200 048

23、12 -0 002 -0 122184200 072由上圖可知，修正后不再存在自相關(guān) 綜上，本研究模型估計(jì)的最終結(jié)果為得至心勺回歸方程為 Y=5.1691+0.5631X1 +0.2821X2 +0.0846X4(0.5250)(6.4152)(15.9286)(8.1883)R2=0.9894Adjusted R-squared =0.9874F=489.0816經(jīng)濟(jì)意義檢驗(yàn)：從經(jīng)濟(jì)意義上來看，該模型說明了在假定其他變量不變的情況下，糧食價(jià)格指數(shù)每上 升1%食品價(jià)格指數(shù)上漲0.5631%;肉禽及制品價(jià)格指數(shù)每上升1%食品價(jià)格指數(shù)上漲 0.2821%;蔬菜價(jià)格指數(shù)每上升1%食品價(jià)格指數(shù)上漲0.

24、0846%=由于各變量都通過了檢 驗(yàn)，所以說明各變量對(duì)被解釋變量都起到了很好的作用。5因果關(guān)系檢驗(yàn)對(duì)x1, y進(jìn)行因果關(guān)系檢驗(yàn)，結(jié)果如下：Pairwise Granger Causality TestsDate: 05/03/14 Time: 21:54Sample: 2014:01 2014:04Lags: 2Null Hypothesis:ObsF-StatisticProbabilityY does not Granger Cause X1251.094030.35409X1 does not Granger Cause Y2.866370.08043由上圖可知，選定顯著性水平(如10%, 0.35>0.1 ,則在該顯著性水平下，接受原 假設(shè)，表示食品價(jià)格指數(shù)對(duì)*M食價(jià)格指數(shù)沒有影響；0.08<0.1 ,拒絕原假設(shè)，表示糧食價(jià)格指數(shù)對(duì)食品價(jià)格指數(shù)有顯著性的影響。對(duì)x2, y進(jìn)行因果關(guān)系檢驗(yàn)，結(jié)果如下：Pairwise Granger Causality Tests Date: 05/03/14 Time: 20:32 Sample: 2014:0